Instructions to use ProKope-AI/ProKope-4B-Eagle-Eye with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ProKope-AI/ProKope-4B-Eagle-Eye with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="ProKope-AI/ProKope-4B-Eagle-Eye")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ProKope-AI/ProKope-4B-Eagle-Eye")
model = AutoModelForMultimodalLM.from_pretrained("ProKope-AI/ProKope-4B-Eagle-Eye", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ProKope-AI/ProKope-4B-Eagle-Eye with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ProKope-AI/ProKope-4B-Eagle-Eye"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProKope-AI/ProKope-4B-Eagle-Eye",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ProKope-AI/ProKope-4B-Eagle-Eye

SGLang

How to use ProKope-AI/ProKope-4B-Eagle-Eye with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ProKope-AI/ProKope-4B-Eagle-Eye" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProKope-AI/ProKope-4B-Eagle-Eye",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ProKope-AI/ProKope-4B-Eagle-Eye" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProKope-AI/ProKope-4B-Eagle-Eye",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ProKope-AI/ProKope-4B-Eagle-Eye with Docker Model Runner:
```
docker model run hf.co/ProKope-AI/ProKope-4B-Eagle-Eye
```

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Access to ProKope-4B-Eagle-Eye weights is provided for academic evaluation, benchmarking, and commercial licensing inquiries. Please provide your affiliation and intended use case to request access.

ProKope-4B-Eagle-Eye

Introduction

ProKope-4B-Eagle-Eye is a 4.2B-parameter multimodal vision-language model developed by ProKope AI for document parsing, structured HTML table reconstruction (rowspan/colspan), mathematical LaTeX transcription, multi-column reading-order extraction, and chart interpretation.

The model uses the Qwen3_5ForConditionalGeneration architecture (4.2B parameters in bfloat16) with a 32K token context window, and loads directly in Hugging Face transformers and vLLM without custom remote code.

Evaluation

Evaluated with deterministic greedy decoding (do_sample=False, 0-shot Pass@1) across standard document OCR and table extraction benchmarks:

Benchmark	Dataset	Split	Metric	ProKope-4B-Eagle-Eye	LightOnOCR-3-4B	Chandra-OCR-2 (4B)	olmOCR-2-7B
PulseBench-Tab	`pulse-ai/PulseBench-Tab`	`train (1,820)`	TEDS Similarity	89.40%	84.40%	78.90%	70.50%
olmOCR-Bench	`allenai/olmOCR-bench`	`test (7 splits)`	Pass Rate	87.06%	86.30%	85.80%	82.40%
ParseBench	`llamaindex/ParseBench`	`test (5 pillars)`	Macro Average	86.01%	75.10%	70.10%	43.30%
fr-bench-pdf2md	`pulsia/fr-bench-pdf2md`	`long_table`	Unit-Test Pass Rate	85.11%	64.00%	72.20%	61.40%
Real5-OmniDocBench	`PaddlePaddle/Real5-OmniDocBench`	`test (5 scenarios)`	Overall Similarity	76.61%	—	—	—

`allenai/olmOCR-bench` Category Breakdown

Category	ProKope-4B-Eagle-Eye	LightOnOCR-3-4B	Chandra-OCR-2 (4B)	olmOCR-2-7B
ArXiv Math (`arxiv_math`)	95.56%	91.10%	86.90%	83.00%
Old Scans Math (`old_scans_math`)	93.10%	89.10%	89.10%	82.30%
Multi-Column (`multi_column`)	92.86%	85.60%	82.10%	83.70%
Old Scans (`old_scans`)	85.19%	52.50%	51.10%	47.70%
Tables (`table_tests`)	85.07%	90.20%	92.10%	84.90%
Long Tiny Text (`long_tiny_text`)	79.41%	93.20%	93.70%	81.90%
Headers & Footers (`headers_footers`)	78.26%	89.20%	91.40%	96.10%
Overall	87.06%	86.30%	85.80%	82.40%

`llamaindex/ParseBench` Pillar Breakdown

Pillar	Metric	ProKope-4B-Eagle-Eye	LightOnOCR-3-4B	Nemotron-3.5-Parse
Table (`table`)	TEDS Similarity	93.95%	83.80%	84.67%
Layout (`layout`)	Reading Order & Content	90.46%	68.30%	70.67%
Text Content (`text_content`)	12-Rule Verbatim Match	87.98%	89.90%	87.96%
Text Formatting (`text_formatting`)	11-Rule Hierarchy & Emphasis	82.51%	67.60%	68.28%
Chart (`chart`)	Label & Value Extraction	75.17%	66.10%	64.40%
Overall (`mean`)	5-Pillar Macro Average	86.01%	75.10%	75.20%

Model Details

Property	Value
Architecture	`Qwen3_5ForConditionalGeneration`
Total Tensor Footprint	`4.2B` combined parameters (`9.08 GB` in `bfloat16`)
Context Length	32,768 tokens
Recommended VRAM	12 GB+ for `bfloat16` inference
Precision	`torch.bfloat16`
License	Apache 2.0 (Weights gated under manual review)

Quickstart

1. Document & Table Extraction (`transformers`)

Requires transformers, torch, and pillow:

import torch
from PIL import Image, ImageOps
from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration

model_id = "ProKope-AI/ProKope-4B-Eagle-Eye"

processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3_5ForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
).eval()

image = Image.open("document_page.png").convert("RGB")
image = ImageOps.autocontrast(image, cutoff=1).resize((1024, 768), Image.Resampling.BILINEAR)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {
                "type": "text",
                "text": "[Visual Geometry: 1024x768px | Domain: complex_grid_table_html]\nExtract all tables and text on this document page into canonical HTML `<table>` structure and Markdown.",
            },
        ],
    }
]

prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[prompt], images=[image], return_tensors="pt").to(model.device)
inputs["pixel_values"] = inputs["pixel_values"].to(torch.bfloat16)

with torch.no_grad():
    generated_ids = model.generate(**inputs, max_new_tokens=1408, do_sample=False, repetition_penalty=1.08)

response = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)

2. Serving with `vLLM`

vllm serve ProKope-AI/ProKope-4B-Eagle-Eye \
  --dtype bfloat16 \
  --max-model-len 16384 \
  --limit-mm-per-prompt image=2

Commercial Licensing & Enterprise Deployment

Access to ProKope-4B-Eagle-Eye weights is gated (manual) for benchmark verification, academic research, and commercial licensing evaluation. Production deployment is available through two options:

Managed Parse API (POST /v1/parse): Pay-as-you-go multi-page PDF and image extraction returning clean Markdown, HTML tables, and structured JSON without managing GPU infrastructure.
Self-Hosted Enterprise Node License: Annual commercial license and turnkey Docker container (vLLM / FastAPI) for private VPC, HIPAA, SOC 2, and air-gapped on-premise deployments on a single 16GB–24GB GPU.

For API keys, enterprise trials, or commercial node licensing, contact prokope.model@gmail.com or submit the gated access form above with your corporate email and intended use case.

Limitations & Intended Use

Intended Use: Document OCR, structured Markdown conversion, HTML table reconstruction (rowspan/colspan), mathematical LaTeX transcription, and chart extraction.
Limitations: Like all vision-language models, outputs on dense rasterized chart annotations (ParseBench [chart]: 75.17%), sub-6pt footnote text (olmOCR-bench [long_tiny_text]: 79.41%), or complex running watermarks (olmOCR-bench [headers_footers]: 78.26%) may contain transcription errors. Verify critical financial or medical outputs independently.

Contact & Citation

Organization: ProKope AI
Authors: Alan Canto, Wesley Foreman
Contact: prokope.model@gmail.com

@misc{canto2026prokope4beagleeye,
  author       = {Alan Canto and Wesley Foreman},
  title        = {ProKope-4B-Eagle-Eye: Multimodal Document Parsing and Table Reconstruction Model},
  howpublished = {Hugging Face},
  year         = {2026},
  url          = {https://huggingface.co/ProKope-AI/ProKope-4B-Eagle-Eye}
}

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

BF16

Datasets used to train ProKope-AI/ProKope-4B-Eagle-Eye

Spaces using ProKope-AI/ProKope-4B-Eagle-Eye 2

Evaluation results

llamaindex/ParseBench leaderboard
Mean View evaluation results

ParseBench 5-pillar enterprise PDF macro average (0-shot Pass@1: 86.01%).
86.01 ^*
Table View evaluation results

93.95
Chart View evaluation results

75.17
allenai/olmOCR-bench leaderboard
Overall View evaluation results

olmOCR-bench overall across 7 document OCR splits (0-shot Pass@1: 87.06%).
87.06 ^*